{"id":"https://openalex.org/W2316560407","doi":"https://doi.org/10.1109/taslp.2016.2584700","title":"Differentiable Pooling for Unsupervised Acoustic Model Adaptation","display_name":"Differentiable Pooling for Unsupervised Acoustic Model Adaptation","publication_year":2016,"publication_date":"2016-06-24","ids":{"openalex":"https://openalex.org/W2316560407","doi":"https://doi.org/10.1109/taslp.2016.2584700","mag":"2316560407"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2584700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2584700","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/9ab370c3-55ac-4554-938f-0a40a818cf45","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pawel Swietojanski","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pawel Swietojanski","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":null,"display_name":"Steve Renals","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.2993,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86402387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"10","first_page":"1773","last_page":"1784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8819000124931335},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5812000036239624},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.5322999954223633},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5026999711990356},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46950000524520874},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.41990000009536743},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4065000116825104}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8819000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652899980545044},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4587000012397766},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4065000116825104},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3970000147819519},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2016.2584700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2584700","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/9ab370c3-55ac-4554-938f-0a40a818cf45","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/9ab370c3-55ac-4554-938f-0a40a818cf45","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Swietojanski, P & Renals, S 2016, 'Differentiable Pooling for Unsupervised Acoustic Model Adaptation', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 24, no. 10, pp. 1773-1784. https://doi.org/10.1109/TASLP.2016.2584700","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1603.09630","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.09630","pdf_url":"https://arxiv.org/pdf/1603.09630","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:publications/9ab370c3-55ac-4554-938f-0a40a818cf45","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/9ab370c3-55ac-4554-938f-0a40a818cf45","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Swietojanski, P & Renals, S 2016, 'Differentiable Pooling for Unsupervised Acoustic Model Adaptation', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 24, no. 10, pp. 1773-1784. https://doi.org/10.1109/TASLP.2016.2584700","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/9ab370c3-55ac-4554-938f-0a40a818cf45","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/9ab370c3-55ac-4554-938f-0a40a818cf45","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Swietojanski, P & Renals, S 2016, 'Differentiable Pooling for Unsupervised Acoustic Model Adaptation', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 24, no. 10, pp. 1773-1784. https://doi.org/10.1109/TASLP.2016.2584700","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W183625566","https://openalex.org/W811578723","https://openalex.org/W1599512239","https://openalex.org/W1770758908","https://openalex.org/W1961429348","https://openalex.org/W1968419113","https://openalex.org/W1979447841","https://openalex.org/W1981617403","https://openalex.org/W1984570643","https://openalex.org/W1985368711","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2012897754","https://openalex.org/W2015633636","https://openalex.org/W2026369565","https://openalex.org/W2036351241","https://openalex.org/W2048526313","https://openalex.org/W2056445351","https://openalex.org/W2056825827","https://openalex.org/W2061305730","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2083751884","https://openalex.org/W2087006792","https://openalex.org/W2089917322","https://openalex.org/W2091987367","https://openalex.org/W2094147890","https://openalex.org/W2105099419","https://openalex.org/W2106051978","https://openalex.org/W2112021726","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2114016253","https://openalex.org/W2116360511","https://openalex.org/W2117951582","https://openalex.org/W2119203697","https://openalex.org/W2125496931","https://openalex.org/W2139427956","https://openalex.org/W2147768505","https://openalex.org/W2147800946","https://openalex.org/W2149194912","https://openalex.org/W2150769028","https://openalex.org/W2153773386","https://openalex.org/W2160306971","https://openalex.org/W2160650576","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2166637769","https://openalex.org/W2169189000","https://openalex.org/W2170541567","https://openalex.org/W2172130635","https://openalex.org/W2239847623","https://openalex.org/W2398054607","https://openalex.org/W2400957076","https://openalex.org/W2402201734","https://openalex.org/W2403731734","https://openalex.org/W2616139854","https://openalex.org/W2962719052","https://openalex.org/W2964182776","https://openalex.org/W6603403951","https://openalex.org/W6603931906","https://openalex.org/W6631362777","https://openalex.org/W6632212032","https://openalex.org/W6637242042","https://openalex.org/W6637565935","https://openalex.org/W6674330103","https://openalex.org/W6677681515","https://openalex.org/W6679429981","https://openalex.org/W6682610290","https://openalex.org/W6683161958","https://openalex.org/W6683965311","https://openalex.org/W6684252548","https://openalex.org/W6686282164","https://openalex.org/W6687511127","https://openalex.org/W6696761078","https://openalex.org/W6712756720","https://openalex.org/W6713250295","https://openalex.org/W6713403589","https://openalex.org/W6713701104","https://openalex.org/W6713823255"],"related_works":[],"abstract_inverted_index":{"We":[0,67,87,129],"present":[1],"a":[2,94],"deep":[3],"neural":[4],"network":[5],"(DNN)":[6],"acoustic":[7,17,102,127],"model":[8,18],"that":[9,89],"includes":[10],"parametrised":[11],"and":[12,52,82,96,147,152],"differentiable":[13,90],"pooling":[14,33,43,51,91],"operators.":[15],"Unsupervised":[16],"adaptation":[19,139,145,154],"is":[20],"cast":[21],"as":[22,65,156,158],"the":[23,27,58,123,133,142,163,168],"problem":[24],"of":[25,42,60,144,162,165,167],"updating":[26],"decision":[28],"boundaries":[29],"implemented":[30],"by":[31],"each":[32,166],"operator.":[34],"In":[35],"particular,":[36],"we":[37],"experiment":[38],"with":[39,104,113],"two":[40],"types":[41],"parametrisations:":[44],"learned":[45],"L":[46],"<sub":[47],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[48],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">p</sub>":[49],"-norm":[50],"weighted":[53],"Gaussian":[54],"pooling,":[55],"in":[56],"which":[57,118],"weights":[59],"both":[61],"operators":[62,92],"are":[63,120],"treated":[64],"speaker-dependent.":[66],"perform":[68],"investigations":[69],"using":[70],"three":[71],"different":[72],"large":[73],"vocabulary":[74],"speech":[75],"recognition":[76],"corpora:":[77],"AMI":[78],"meetings,":[79],"TED":[80],"talks,":[81],"Switchboard":[83],"conversational":[84],"telephone":[85],"speech.":[86],"demonstrate":[88],"provide":[93],"robust":[95],"relatively":[97],"low-dimensional":[98],"way":[99],"to":[100,115,149],"adapt":[101],"models,":[103],"relative":[105],"word":[106],"error":[107],"rates":[108],"reductions":[109],"ranging":[110],"from":[111],"5-20%":[112],"respect":[114],"unadapted":[116],"systems,":[117],"themselves":[119],"better":[121],"than":[122],"baseline":[124],"fully-connected":[125],"DNN-based":[126],"models.":[128],"also":[130],"investigate":[131],"how":[132],"proposed":[134,169],"techniques":[135],"work":[136],"under":[137],"various":[138],"conditions":[140],"including":[141],"quality":[143],"data":[146],"complementarity":[148],"other":[150],"feature-":[151],"model-space":[153],"methods,":[155],"well":[157],"providing":[159],"an":[160],"analysis":[161],"characteristics":[164],"approaches.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}